INDEX

Explanations

profanity and insults

oai_token-act-pair · gpt-3.5-turbo

sentences that convey strong opinions or critiques

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 enrol

-0.82

 emanc

-0.77

isbury

-0.76

 jointly

-0.75

 exclusively

-0.71

 authorized

-0.71

 extensively

-0.70

 interpreter

-0.70

 footing

-0.69

eteenth

-0.68

POSITIVE LOGITS

 Anyway

1.39

 Especially

1.28

;)

1.25

 Seriously

1.20

Anyway

1.19

 Thankfully

1.19

 Maybe

1.16

 Luckily

1.15

 Besides

1.13

 That

1.11

Activations Density 0.797%

profanity and insults

sentences that convey strong opinions or critiques

No Comments

No Known Activations